AutoPartGen: autogressive 3D part generation and discovery

Conference item

We introduce AutoPartGen, a model that generates objects composed of 3D parts in an autoregressive manner. This model can take as input an image of an object, 2D masks of the object’s parts, or an existing 3D object, and generate a corresponding compositional 3D reconstruction. Our approach builds upon 3DShape2VecSet, a recent latent 3D representation with powerful geometric expressiveness. We observe that this latent space exhibits strong compositional properties, making it particularly well-suited for part-based generation tasks. Specifically, AutoPartGen generates object parts autoregressively, predicting one part at a time while conditioning on previously generated parts and additional inputs, such as 2D images, masks, or 3D objects. This process continues until the model decides that all parts have been generated, thus determining automatically the type and number of parts. The resulting parts can be seamlessly assembled into coherent objects or scenes without requiring additional optimization. We evaluate both the overall 3D generation capabilities and the part-level generation quality of AutoPartGen, demonstrating that it achieves state-of-the-art performance in 3D part generation.

Authors: Chen, M; Wang, J; Shapovalov, R; Monnier, T; Jung, H

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Neural Information Processing Systems Foundation
• Host title: Advances in Neural Information Processing Systems 38
• Publication date: 2026-05-01
• Acceptance date: 2025-09-18
• Event title: 39th Conference on Neural Information Processing Systems (NeurIPS 2025)
• Event location: San Diego, California, USA and Mexico City, Mexico
• Event website: https://neurips.cc/Conferences/2025
• Event start date: 2025-11-30
• Event end date: 2025-12-07
• Language: English